1filellm VS llama.cpp

I created something similar, https://github.com/jimmc414/1filellm

It converts papers, repositories, PRs and web docs into one text file for llm ingestion

I created a cli tool that copies a GitHub or local repo into a text file for llm ingestion. It only pulls the filetypes you specify.

https://github.com/jimmc414/1filellm

Nice. I guess we are all thinking the same things. I created something similar today where you can choose the file extensions to pull and handles Jupiter notebooks pulling only text and code. I included a script to strip out superfluous characters, stop words, and converts everything to lowercase.

It also works if you supply a local folder of source files instead of a github repo.

https://github.com/jimmc414/onefilerepo

if you can compile stuff, then looking at llama.cpp (what ollama uses) is also interesting: https://github.com/ggerganov/llama.cpp

the server is here: https://github.com/ggerganov/llama.cpp/tree/master/examples/...

And you can search for any GGUF on huggingface

Yes, Metal seems to allow a maximum of 1/2 of the RAM for one process, and 3/4 of the RAM allocated to the GPU overall. There’s a kernel hack to fix it, but that comes with the usual system integrity caveats. https://github.com/ggerganov/llama.cpp/discussions/2182

For anyone interested in exploring this, llama.cpp has an example implementation here:

https://github.com/ggerganov/llama.cpp/tree/master/examples/...

Getting started with LLMs can be intimidating. In this tutorial we will show you how to fine-tune a large language model using LoRA, facilitated by tools like llama.cpp and KitOps.

well https://github.com/ggerganov/llama.cpp/issues/6849